vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(server): infinite loop to inference

Browse source
This commit is contained in:
Riceball LEE 2024-02-14 07:40:51 +08:00
parent f5ca054855
commit 4447e95ec5
No known key found for this signature in database
GPG key ID: 10F15E84852CB868
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -1737,6 +1737,8 @@ struct llama_server_context
{ {
// if you get here, it means the KV cache is full - try increasing it via the context size // if you get here, it means the KV cache is full - try increasing it via the context size
LOG_TEE("%s : failed to decode the batch, n_batch = %d, ret = %d\n", __func__, n_batch, ret); LOG_TEE("%s : failed to decode the batch, n_batch = %d, ret = %d\n", __func__, n_batch, ret);
LOG_ERROR("KV cache is full - try increasing it via the context size", {{"ctx-size", params.n_ctx}});
kv_cache_clear();
return false; return false;
} }